© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77633
    Prev
    Next
    INDEX
    Explanations

    visual presentation of food

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on words and phrases describing visual appeal—especially color and aesthetic descriptors (e.g., pretty, vibrant, colorful, aesthetic).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ンテージ
    -1.16
     flavored
    -0.92
    csv
    -0.91
     ябло
    -0.90
     yaiba
    -0.90
    ώς
    -0.88
    ּוֹ
    -0.85
    óngase
    -0.85
    formula
    -0.82
     bagels
    -0.81
    POSITIVE LOGITS
     presentation
    2.41
     visually
    1.92
    Presentation
    1.88
    presentation
    1.76
     Presentation
    1.73
     appearance
    1.64
     plating
    1.63
     visual
    1.62
     presentations
    1.59
     presentación
    1.57
    Activations Density 0.033%

    No Known Activations